R Notebook
#import libraries
library(dplyr)
library(readr)
library (visdat)
library(superml)
#import data file & preview data
df <- read_csv('/Users/Amanda.Hartzler/Desktop/Data_Analytics_Masters/D206/churn_raw_data.csv')New names:
• `` -> `...1`
Rows: 10000 Columns: 52
── Column specification ─────────────────────────────────────────────────────────
Delimiter: ","
chr (28): Customer_id, Interaction, City, State, County, Area, Timezone, Job,...
dbl (24): ...1, CaseOrder, Zip, Lat, Lng, Population, Children, Age, Income, ...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.head(df)#determine column names, non-null values, & types
str(df)spec_tbl_df [10,000 × 52] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
$ ...1 : num [1:10000] 1 2 3 4 5 6 7 8 9 10 ...
$ CaseOrder : num [1:10000] 1 2 3 4 5 6 7 8 9 10 ...
$ Customer_id : chr [1:10000] "K409198" "S120509" "K191035" "D90850" ...
$ Interaction : chr [1:10000] "aa90260b-4141-4a24-8e36-b04ce1f4f77b" "fb76459f-c047-4a9d-8af9-e0f7d4ac2524" "344d114c-3736-4be5-98f7-c72c281e2d35" "abfa2b40-2d43-4994-b15a-989b8c79e311" ...
$ City : chr [1:10000] "Point Baker" "West Branch" "Yamhill" "Del Mar" ...
$ State : chr [1:10000] "AK" "MI" "OR" "CA" ...
$ County : chr [1:10000] "Prince of Wales-Hyder" "Ogemaw" "Yamhill" "San Diego" ...
$ Zip : num [1:10000] 99927 48661 97148 92014 77461 ...
$ Lat : num [1:10000] 56.3 44.3 45.4 33 29.4 ...
$ Lng : num [1:10000] -133.4 -84.2 -123.2 -117.2 -95.8 ...
$ Population : num [1:10000] 38 10446 3735 13863 11352 ...
$ Area : chr [1:10000] "Urban" "Urban" "Urban" "Suburban" ...
$ Timezone : chr [1:10000] "America/Sitka" "America/Detroit" "America/Los_Angeles" "America/Los_Angeles" ...
$ Job : chr [1:10000] "Environmental health practitioner" "Programmer, multimedia" "Chief Financial Officer" "Solicitor" ...
$ Children : num [1:10000] NA 1 4 1 0 3 0 2 2 NA ...
$ Age : num [1:10000] 68 27 50 48 83 83 NA NA 49 86 ...
$ Education : chr [1:10000] "Master's Degree" "Regular High School Diploma" "Regular High School Diploma" "Doctorate Degree" ...
$ Employment : chr [1:10000] "Part Time" "Retired" "Student" "Retired" ...
$ Income : num [1:10000] 28562 21705 NA 18925 40074 ...
$ Marital : chr [1:10000] "Widowed" "Married" "Widowed" "Married" ...
$ Gender : chr [1:10000] "Male" "Female" "Female" "Male" ...
$ Churn : chr [1:10000] "No" "Yes" "No" "No" ...
$ Outage_sec_perweek : num [1:10000] 6.97 12.01 10.25 15.21 8.96 ...
$ Email : num [1:10000] 10 12 9 15 16 15 10 16 20 18 ...
$ Contacts : num [1:10000] 0 0 0 2 2 3 0 0 2 1 ...
$ Yearly_equip_failure: num [1:10000] 1 1 1 0 1 1 1 0 3 0 ...
$ Techie : chr [1:10000] "No" "Yes" "Yes" "Yes" ...
$ Contract : chr [1:10000] "One year" "Month-to-month" "Two Year" "Two Year" ...
$ Port_modem : chr [1:10000] "Yes" "No" "Yes" "No" ...
$ Tablet : chr [1:10000] "Yes" "Yes" "No" "No" ...
$ InternetService : chr [1:10000] "Fiber Optic" "Fiber Optic" "DSL" "DSL" ...
$ Phone : chr [1:10000] "Yes" "Yes" "Yes" "Yes" ...
$ Multiple : chr [1:10000] "No" "Yes" "Yes" "No" ...
$ OnlineSecurity : chr [1:10000] "Yes" "Yes" "No" "Yes" ...
$ OnlineBackup : chr [1:10000] "Yes" "No" "No" "No" ...
$ DeviceProtection : chr [1:10000] "No" "No" "No" "No" ...
$ TechSupport : chr [1:10000] "No" "No" "No" "No" ...
$ StreamingTV : chr [1:10000] "No" "Yes" "No" "Yes" ...
$ StreamingMovies : chr [1:10000] "Yes" "Yes" "Yes" "No" ...
$ PaperlessBilling : chr [1:10000] "Yes" "Yes" "Yes" "Yes" ...
$ PaymentMethod : chr [1:10000] "Credit Card (automatic)" "Bank Transfer(automatic)" "Credit Card (automatic)" "Mailed Check" ...
$ Tenure : num [1:10000] 6.8 1.16 15.75 17.09 1.67 ...
$ MonthlyCharge : num [1:10000] 171 243 159 120 151 ...
$ Bandwidth_GB_Year : num [1:10000] 905 801 2055 2165 271 ...
$ item1 : num [1:10000] 5 3 4 4 4 3 6 2 5 2 ...
$ item2 : num [1:10000] 5 4 4 4 4 3 5 2 4 2 ...
$ item3 : num [1:10000] 5 3 2 4 4 3 6 2 4 2 ...
$ item4 : num [1:10000] 3 3 4 2 3 2 4 5 3 2 ...
$ item5 : num [1:10000] 4 4 4 5 4 4 1 2 4 5 ...
$ item6 : num [1:10000] 4 3 3 4 4 3 5 3 3 2 ...
$ item7 : num [1:10000] 3 4 3 3 4 3 5 4 4 3 ...
$ item8 : num [1:10000] 4 4 3 3 5 3 5 5 4 3 ...
- attr(*, "spec")=
.. cols(
.. ...1 = col_double(),
.. CaseOrder = col_double(),
.. Customer_id = col_character(),
.. Interaction = col_character(),
.. City = col_character(),
.. State = col_character(),
.. County = col_character(),
.. Zip = col_double(),
.. Lat = col_double(),
.. Lng = col_double(),
.. Population = col_double(),
.. Area = col_character(),
.. Timezone = col_character(),
.. Job = col_character(),
.. Children = col_double(),
.. Age = col_double(),
.. Education = col_character(),
.. Employment = col_character(),
.. Income = col_double(),
.. Marital = col_character(),
.. Gender = col_character(),
.. Churn = col_character(),
.. Outage_sec_perweek = col_double(),
.. Email = col_double(),
.. Contacts = col_double(),
.. Yearly_equip_failure = col_double(),
.. Techie = col_character(),
.. Contract = col_character(),
.. Port_modem = col_character(),
.. Tablet = col_character(),
.. InternetService = col_character(),
.. Phone = col_character(),
.. Multiple = col_character(),
.. OnlineSecurity = col_character(),
.. OnlineBackup = col_character(),
.. DeviceProtection = col_character(),
.. TechSupport = col_character(),
.. StreamingTV = col_character(),
.. StreamingMovies = col_character(),
.. PaperlessBilling = col_character(),
.. PaymentMethod = col_character(),
.. Tenure = col_double(),
.. MonthlyCharge = col_double(),
.. Bandwidth_GB_Year = col_double(),
.. item1 = col_double(),
.. item2 = col_double(),
.. item3 = col_double(),
.. item4 = col_double(),
.. item5 = col_double(),
.. item6 = col_double(),
.. item7 = col_double(),
.. item8 = col_double()
.. )
- attr(*, "problems")=<externalptr> #determine if any rows are duplicated
duplicated(df) [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[109] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[145] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[157] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[169] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[181] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[193] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[205] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[217] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[229] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[241] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[253] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[265] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[277] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[289] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[301] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[313] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[325] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[337] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[349] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[361] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[373] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[385] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[397] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[409] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[421] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[433] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[445] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[457] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[469] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[481] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[493] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[505] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[517] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[529] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[541] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[553] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[565] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[577] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[589] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[601] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[613] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[625] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[637] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[649] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[661] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[673] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[685] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[697] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[709] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[721] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[733] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[745] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[757] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[769] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[781] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[793] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[805] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[817] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[829] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[841] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[853] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[865] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[877] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[889] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[901] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[913] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[925] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[937] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[949] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[961] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[973] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[985] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[997] FALSE FALSE FALSE FALSE
[ reached getOption("max.print") -- omitted 9000 entries ]#delete any duplicated rows
df <- distinct(df)
print(df)#no duplicated values in dataset
#determine which variables contain null values & how many null values
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 2495
Age Education Employment
2475 0 0
Income Marital Gender
2490 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 931
MonthlyCharge Bandwidth_GB_Year item1
0 1021 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #visualization of missing data
vis_miss(df)
#Check each column containing null values that is a float or integer value.
#Determine skew, possible ouliers, and distribution.
#Children Histogram
hist(df$Children,
main = 'Children',
xlab = 'Number of Children',
border = 'blue',
col = 'green',
xlim = c(0, 10),
breaks = 10)
#Age Histogram
hist(df$Age)
#Income Histogram
hist(df$Income)
#Tenure Histogram
hist(df$Tenure)
hist(df$Tenure)
#Children column is right skewed, therefore I will use the median to impute the data.
df$Children[is.na(df$Children)]<-median(df$Children,na.rm=TRUE)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
2475 0 0
Income Marital Gender
2490 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 931
MonthlyCharge Bandwidth_GB_Year item1
0 1021 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Check if the distribution of data was effected by the imputation of the median.
hist(df$Children)
#Age column has a uniform distribution, therefore I will use the mean to impute the data.
df$Age[is.na(df$Age)]<-mean(df$Age,na.rm=TRUE)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
2490 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 931
MonthlyCharge Bandwidth_GB_Year item1
0 1021 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Check if the distribution of data was effected by the imputation of the mean.
hist(df$Age)
#Income column has is right skewed, therefore I will use the median to impute the data.
df$Income[is.na(df$Income)]<-median(df$Income,na.rm=TRUE)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 931
MonthlyCharge Bandwidth_GB_Year item1
0 1021 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Check if the distribution of data was effected by the imputation of the median.
hist(df$Income)
#Tenure column has a bimodal distribution, therefore I decided to use the median to impute the data. (Middleton, 2022a)
df$Tenure[is.na(df$Tenure)]<-median(df$Tenure,na.rm=TRUE)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 0
MonthlyCharge Bandwidth_GB_Year item1
0 1021 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Check if the distribution of data was effected by the imputation of the mean.
hist(df$Tenure)
#Bandwidth_GB_Year column has a bimodal distribution, therefore I decided to use the median to impute the data.
df$Bandwidth_GB_Year[is.na(df$Bandwidth_GB_Year)]<-median(df$Bandwidth_GB_Year,na.rm=TRUE)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 2477
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 0
MonthlyCharge Bandwidth_GB_Year item1
0 0 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Check if the distribution of data was effected by the imputation of the mean.
hist(df$Bandwidth_GB_Year)
#Clean null values from object or text columns using the mode.
#Techie column is text, therefore I will use the mode to impute the data.
df$Techie[is.na(df$Techie)]<-mode(df$Techie)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 0
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 1026 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 0
MonthlyCharge Bandwidth_GB_Year item1
0 0 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #Phone column is text, therefore I will use the mode to impute the data.
df$Phone[is.na(df$Phone)]<-mode(df$Phone)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 0
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 0 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
991 0 0
PaperlessBilling PaymentMethod Tenure
0 0 0
MonthlyCharge Bandwidth_GB_Year item1
0 0 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 #TechSupport column is text, therefore I will use the mode to impute the data.
df$TechSupport[is.na(df$TechSupport)]<-mode(df$TechSupport)
#verify the data was imputed
colSums(is.na(df)) ...1 CaseOrder Customer_id
0 0 0
Interaction City State
0 0 0
County Zip Lat
0 0 0
Lng Population Area
0 0 0
Timezone Job Children
0 0 0
Age Education Employment
0 0 0
Income Marital Gender
0 0 0
Churn Outage_sec_perweek Email
0 0 0
Contacts Yearly_equip_failure Techie
0 0 0
Contract Port_modem Tablet
0 0 0
InternetService Phone Multiple
0 0 0
OnlineSecurity OnlineBackup DeviceProtection
0 0 0
TechSupport StreamingTV StreamingMovies
0 0 0
PaperlessBilling PaymentMethod Tenure
0 0 0
MonthlyCharge Bandwidth_GB_Year item1
0 0 0
item2 item3 item4
0 0 0
item5 item6 item7
0 0 0
item8
0 b <-boxplot(df$CaseOrder)
#Using Boxplots, check for outliers in each in each float or integer value column.
b <-boxplot(df$Zip, main = 'Zip')
b <-boxplot(df$Lat, main = 'Lat')
b <-boxplot(df$Lng, main = 'Lng')
b <-boxplot(df$Population, main = 'Population')
b <-boxplot(df$Children, main = 'Children')
b <-boxplot(df$Age, main = 'Age')
b <-boxplot(df$Income, main = 'Income')
b <-boxplot(df$Outage_sec_perweek, main = 'Outage_sec_perweek')
b <-boxplot(df$Email, main = 'Email')
b <-boxplot(df$Contacts, main = 'Contacts')
b <-boxplot(df$Yearly_equip_failure, main = 'Yearly_equip_failure')
b <-boxplot(df$Tenure, main = 'Tenure')
b <-boxplot(df$MonthlyCharge, main = 'MonthlyCharge')
b <-boxplot(df$Bandwidth_GB_Year, main = 'Bandwidth_GB_Year')
b <-boxplot(df$item1, main = 'item1')
b <-boxplot(df$item2, main = 'item2')
b <-boxplot(df$item3, main = 'item3')
b <-boxplot(df$item4, main = 'item4')
b <-boxplot(df$item5, main = 'item5')
b <-boxplot(df$item6, main = 'item6')
b <-boxplot(df$item7, main = 'item7')
b <-boxplot(df$item8, main = 'item8')
#Outliers found in Lat, Lng, Population, Children, Income, Outage_sec_perweek, Email, Contacts, Yearly_equip_failure, MonthlyCharge, item1, item2, item3, item4, item5, item6, item7, & item8 columns.
#Treating outliers:
max(df$Lat)[1] 70.64066min(df$Lat)[1] 17.96612#Retain outliers in Lat (Incuding US territories, the min and max are within a valid range) (Bathman, 2018)
max(df$Lng)[1] -65.66785min(df$Lng)[1] -171.6882#Retain outliers in Lng (Incuding US territories, the min and max are within a valid range) (Bathman, 2018)
summary(df$Population) Min. 1st Qu. Median Mean 3rd Qu. Max.
0 738 2910 9757 13168 111850 #Replace outlier population values > 27,000
#New York City, NY, has the most density population in the US. In New York the max population density is a little over 27,000 per square mile. Therefore the right skewed outliers are likely entry errors. (Planning-Population-NYC Population Facts - DCP, n.d.)
df["Population"][df["Population"] >= 27000] <- 2931
summary(df$Population) Min. 1st Qu. Median Mean 3rd Qu. Max.
0 738 2910 4949 5943 26999 #Check distribution of population data.
b <-boxplot(df$Population, main = 'Population')
#Check that the max income is within a reasonable range
max(df$Income)[1] 258900.7#Check that the max and min outage_sec_perweek is within a reasonable range
max(df$Outage_sec_perweek)[1] 47.04928min(df$Outage_sec_perweek)[1] -1.348571#Retain outliers in Children (All values are possible children values)
#Retain outliers in Income (All values are possible income values)
summary(df$Outage_sec_perweek) Min. 1st Qu. Median Mean 3rd Qu. Max.
-1.349 8.054 10.203 11.453 12.488 47.049 #Replace negative outliers in Outage_sec_perweek with median because you cannot have less than zero secons of outage
df$Outage_sec_perweek[df$Outage_sec_perweek <0] <- 10.214231
summary(df$Population) Min. 1st Qu. Median Mean 3rd Qu. Max.
0 738 2910 4949 5943 26999 b <-boxplot(df$Outage_sec_perweek, main = 'Outage_sec_perweek')
#Check that the MonthlyCharge income is within a reasonable range
max(df$MonthlyCharge)[1] 315.8786#Retain outliers in Email (All values are possible email values)
#Retain outliers in Contacts (All values are possible contact values)
#Retain outliers in Yearly_equip_failure (All values are possible equipment failure values)
#Retain outliers in MonthlyCharge (All values are possible monthly charge values)
#Retain outliers in all item answers (All values are possible values for each item answer)#Re-expressing Categorical Variables (Middleton, 2022c)
#Practice label encoding yes/no dichotomous binary columns. (By Great Learning Team -, 2022)
lbl = LabelEncoder$new()
df$Churn = lbl$fit_transform(df$Churn)
print(df$Churn) [1] 0 1 0 0 1 0 1 1 0 0 0 0 0 0 1 1 1 1 0 1 0 0 0 0 1 1 1 1 1 1 0 0 1 1 1 1 1
[38] 0 0 0 0 0 1 0 1 1 1 1 0 0 1 1 0 1 1 0 1 0 1 0 0 0 1 0 0 0 1 1 0 1 1 1 0 1
[75] 1 1 1 0 1 0 1 0 0 0 0 0 0 1 1 0 1 1 0 1 0 1 0 1 0 0 1 0 1 0 1 1 1 1 1 1 0
[112] 1 1 0 1 0 0 0 1 1 0 1 0 0 0 0 1 0 0 1 1 0 1 1 0 0 0 0 1 1 0 1 0 0 1 1 1 0
[149] 1 1 1 0 0 1 0 0 1 0 1 0 1 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 1 0 0 1 1 0 1 1
[186] 0 0 1 0 0 0 1 1 0 1 1 0 0 0 0 1 1 1 0 0 1 0 0 1 0 0 0 0 0 1 0 0 0 0 0 1 1
[223] 1 0 1 0 1 0 1 1 1 0 1 0 0 0 1 1 0 1 0 0 0 1 1 0 0 0 0 0 0 0 1 1 1 1 0 0 0
[260] 1 1 1 0 0 1 1 1 1 1 1 0 1 1 0 0 0 0 0 1 1 1 0 1 1 1 0 1 0 1 0 1 0 0 1 1 0
[297] 0 0 0 1 0 0 1 1 0 1 0 0 0 0 0 1 0 0 0 0 1 1 1 0 0 0 1 0 1 0 1 1 0 1 1 1 1
[334] 0 0 0 1 1 0 1 1 0 0 1 0 1 0 1 1 1 1 0 0 1 1 0 1 0 1 0 0 1 0 1 0 0 1 0 0 1
[371] 0 0 0 0 1 1 0 1 0 1 0 1 0 0 1 0 0 1 1 1 1 1 1 1 1 0 1 0 1 0 1 1 0 1 0 0 0
[408] 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 0 1 1 1 0 1 0 0 1 0 1 1
[445] 0 1 1 0 1 0 0 0 0 0 0 1 1 0 0 0 1 0 1 0 0 1 0 1 0 0 1 1 0 0 1 1 0 0 1 0 0
[482] 1 0 0 1 0 1 1 0 1 1 1 0 0 0 1 1 1 0 1 0 1 0 1 1 1 0 0 1 0 0 0 1 1 1 1 1 0
[519] 0 1 0 1 0 0 1 1 1 1 0 1 0 0 1 0 0 0 1 0 0 0 0 0 1 1 1 0 1 0 1 1 1 0 1 1 0
[556] 0 0 1 1 0 1 1 1 0 0 0 0 0 1 1 0 0 1 1 1 1 0 0 0 0 0 1 0 0 0 0 1 0 1 0 0 1
[593] 1 0 1 1 1 0 0 0 0 1 0 0 0 1 0 1 1 1 1 1 0 0 1 0 1 1 0 0 1 1 0 0 1 1 1 0 0
[630] 0 1 1 0 0 1 1 0 1 1 1 1 1 0 0 1 1 0 1 0 0 1 0 1 1 1 0 0 0 1 0 1 0 0 1 1 0
[667] 0 0 0 0 1 1 0 1 1 1 0 0 0 0 0 1 0 0 0 1 0 1 0 1 0 0 0 0 0 1 1 1 1 1 0 0 1
[704] 1 0 0 0 1 1 1 1 0 0 1 0 0 1 1 1 0 0 1 0 0 1 1 0 0 0 1 0 1 1 0 0 0 1 1 0 1
[741] 0 0 0 0 0 1 0 0 1 0 0 1 0 0 1 1 0 1 1 0 0 0 0 0 0 0 1 0 0 0 1 1 0 0 0 0 0
[778] 1 0 1 0 1 1 1 0 0 1 0 0 1 1 0 0 1 1 1 1 1 1 0 1 1 1 0 1 0 0 0 1 1 1 0 1 1
[815] 0 0 1 0 0 1 1 1 1 0 1 1 1 0 0 1 0 1 1 0 1 1 0 0 0 0 1 0 1 1 0 0 0 1 1 0 1
[852] 1 1 1 0 1 1 0 1 0 0 0 1 1 0 1 1 1 0 0 1 0 1 1 1 1 1 1 0 1 0 1 0 1 0 0 0 1
[889] 0 1 0 1 0 0 0 0 0 0 0 0 1 1 0 0 0 1 1 0 0 1 0 1 0 1 1 0 0 1 0 1 1 0 0 1 0
[926] 1 1 1 1 0 0 0 1 0 1 0 0 0 0 1 1 1 1 1 1 1 1 0 1 0 0 1 1 1 1 1 0 1 0 0 1 0
[963] 0 1 0 1 1 1 0 0 0 0 1 1 1 0 1 1 0 1 0 1 0 1 0 1 1 1 1 0 1 0 1 0 1 1 1 0 0
[1000] 1
[ reached getOption("max.print") -- omitted 9000 entries ]df$Techie = lbl$fit_transform(df$Techie)
df$Port_modem = lbl$fit_transform(df$Port_modem)
df$Phone = lbl$fit_transform(df$Phone)#Practice Ordinal Encoding (Middleton, 2022c)
#First find unique entiries in the education table.
print(unique(df$Education)) [1] "Master's Degree"
[2] "Regular High School Diploma"
[3] "Doctorate Degree"
[4] "No Schooling Completed"
[5] "Associate's Degree"
[6] "Bachelor's Degree"
[7] "Some College, Less than 1 Year"
[8] "GED or Alternative Credential"
[9] "Some College, 1 or More Years, No Degree"
[10] "9th Grade to 12th Grade, No Diploma"
[11] "Nursery School to 8th Grade"
[12] "Professional School Degree" print(length(unique(df$Education)))[1] 12edu.num <- revalue(x = df$Education, replace = c('No Schooling Completed'= 0, 'Nursery School to 8th Grade'= 1, '9th Grade to 12th Grade, No Diploma'= 2, 'GED or Alternative Credential'= 3, 'Regular High School Diploma'= 4, 'Some College, Less than 1 Year'= 5, 'Some College, 1 or More Years, No Degree'= 6, "Associate's Degree"= 7, 'Professional School Degree'= 8, "Bachelor's Degree"= 9, "Master's Degree"= 10, 'Doctorate Degree'= 11))
df$Education_numeric <- as.numeric(edu.num)#Check that Education_numeric was created correctly.
unique(df$Education_numeric) [1] 10 4 11 0 7 9 5 3 6 2 1 8#Principal Component Analysis
data.frame(colnames(df))#Principal Component Analysis
features <- df[,c(8, 9, 10, 11, 15, 16, 19, 23, 24, 25, 26, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52)]
print(features)df.pca<- prcomp(df[,c(8, 9, 10, 11, 15, 16, 19, 23, 24, 25, 26, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52)], center = TRUE, scale = TRUE)df.pca$rotation PC1 PC2 PC3 PC4
Zip 0.0188571537 -0.6401960693 0.2745147405 0.044817773
Lat 0.0015986087 -0.0630604684 0.0065279851 0.007661462
Lng -0.0168198338 0.6456309318 -0.2749570864 -0.043551367
Population -0.0002513100 0.0965502290 -0.0529230067 -0.014276309
Children -0.0007364960 0.0265449717 -0.0127067734 0.007702000
Age -0.0050703280 -0.0040857303 -0.0126322662 -0.017399437
Income 0.0008734781 0.0022717013 0.0073997800 0.024225479
Outage_sec_perweek 0.0137353655 -0.0001948383 0.0192716284 -0.047172817
Email -0.0088188377 0.0043371779 -0.0244117269 -0.006065079
Contacts 0.0084514444 0.0103492406 -0.0004317492 -0.011705395
Yearly_equip_failure 0.0078611636 -0.0048470968 0.0197746873 0.008368691
Tenure 0.0105528765 0.2718806419 0.6462878770 -0.069427075
MonthlyCharge 0.0004178732 0.0281393263 0.0348137800 -0.025584901
Bandwidth_GB_Year 0.0124697625 0.2723041111 0.6479502878 -0.071668858
item1 -0.4589214311 0.0283580145 0.0217145869 0.279398233
item2 -0.4339234191 0.0161364593 0.0388539635 0.282013824
item3 -0.4008361003 0.0256498788 0.0259608159 0.280485297
item4 -0.1454553593 -0.0538598694 -0.0300107138 -0.565912750
item5 0.1753227142 0.0584312697 0.0453129572 0.585224442
item6 -0.4046633995 -0.0362809058 0.0028431418 -0.181950796
item7 -0.3580687534 -0.0214747589 0.0056640371 -0.179712058
item8 -0.3086035826 -0.0214406866 -0.0085830524 -0.131865011
PC5 PC6 PC7 PC8
Zip 0.106838112 -0.071943611 -0.031718948 -0.0004918139
Lat -0.604092714 0.349158401 0.176803170 -0.0123467531
Lng -0.022622852 0.021301121 0.005119094 -0.0023274569
Population 0.535630824 -0.363897908 -0.109653344 -0.1422587510
Children -0.165598608 0.099441337 -0.558512211 0.0662076838
Age 0.072020765 0.004859611 0.490109311 -0.3405078047
Income -0.051800439 0.034237938 -0.167306173 -0.4106327753
Outage_sec_perweek -0.404985165 -0.575669020 -0.041002499 -0.0218139633
Email 0.088798643 -0.126891598 0.108678091 0.6562666245
Contacts 0.045884979 -0.025840089 0.525484143 -0.1569462869
Yearly_equip_failure -0.043414321 -0.034792506 -0.276182910 -0.4799535253
Tenure 0.030263895 0.048458906 0.017542333 0.0114757926
MonthlyCharge -0.348089364 -0.606043975 0.084388516 -0.0109985176
Bandwidth_GB_Year 0.001008189 0.009490080 -0.005957515 0.0153956264
item1 -0.027406246 -0.020132836 -0.001442801 -0.0063828301
item2 -0.013106446 -0.014528708 0.020744519 -0.0102293745
item3 -0.005955447 0.017962674 0.006202985 0.0371669811
item4 -0.017172468 0.049138274 0.012216257 0.0076772156
item5 -0.005891339 -0.027717791 0.037297888 -0.0021468644
item6 0.013371009 -0.016879375 -0.008886825 -0.0041392987
item7 -0.001126029 0.039892820 -0.009188857 -0.0050021568
item8 0.038893665 -0.062066492 -0.002840167 -0.0488327490
PC9 PC10 PC11 PC12
Zip 0.0055109415 0.0221390539 0.009438189 0.033803067
Lat 0.0581594889 -0.1097768024 -0.031036062 -0.105859420
Lng -0.0179312580 -0.0008572831 -0.001855791 -0.015524618
Population 0.1341556756 -0.1122017062 0.011749835 0.049976673
Children -0.0205626410 0.4926453257 0.110650090 0.606937815
Age -0.2540765071 0.3580634821 -0.578105966 0.305043406
Income 0.7017492092 0.3622854173 -0.194644508 -0.344725352
Outage_sec_perweek 0.0137585505 0.0067931275 0.025849450 -0.068991878
Email -0.0833625663 0.5638131180 -0.116309932 -0.403100609
Contacts 0.1353550498 0.3220837334 0.745542585 0.118774412
Yearly_equip_failure -0.6257293487 0.2089272189 0.189844040 -0.445385778
Tenure -0.0025325675 0.0070834454 -0.020093179 -0.011219673
MonthlyCharge 0.0220788308 -0.0390286833 -0.062021370 0.149885637
Bandwidth_GB_Year 0.0046265327 0.0038654878 0.001363421 0.008910929
item1 -0.0172336042 -0.0037040449 0.020718797 -0.001922596
item2 0.0016762503 -0.0003780297 0.005721930 0.012343377
item3 -0.0227616807 -0.0190900159 -0.008295027 -0.015952850
item4 -0.0174267533 -0.0266739621 0.003271266 -0.017267919
item5 -0.0061626124 -0.0097481196 -0.005244191 0.008040304
item6 0.0019448269 0.0224055595 0.015233095 -0.005862493
item7 0.0465036490 0.0428836523 0.030152756 -0.012092638
item8 -0.0003514868 -0.0476998738 -0.049361376 0.036070714
PC13 PC14 PC15 PC16
Zip 0.002398198 -0.029410986 -0.012341937 -0.006171460
Lat -0.200539009 0.623343169 0.088236550 -0.006956204
Lng 0.029222817 -0.084953496 -0.002360124 0.006683356
Population -0.170707780 0.685233124 -0.030816956 -0.028835015
Children -0.019747722 0.133306417 0.026084326 -0.038932222
Age 0.092018620 0.069357260 -0.061502206 0.009482201
Income -0.039235083 -0.114781714 0.010126312 -0.058475688
Outage_sec_perweek 0.671522878 0.164355291 -0.123329097 0.011729552
Email -0.087028745 0.134842637 0.072635999 -0.017544960
Contacts 0.013622041 0.007555721 0.037937409 -0.036263403
Yearly_equip_failure -0.132347740 0.027762683 0.033070138 0.004632331
Tenure 0.031470595 0.027990666 0.001781114 -0.010329713
MonthlyCharge -0.647093332 -0.220846643 0.051143892 0.010318362
Bandwidth_GB_Year -0.015457712 0.012860605 0.013654264 0.001989609
item1 -0.010487739 0.008139223 -0.068894261 -0.118697523
item2 -0.006639538 0.020223318 -0.110396306 -0.171608143
item3 -0.007350790 -0.025935685 -0.174121213 -0.246669351
item4 -0.020931980 -0.024711910 -0.170593451 -0.476036125
item5 0.045398292 -0.002254260 0.130339171 0.062747564
item6 -0.005335058 0.010159585 -0.066314788 0.058500232
item7 -0.032120564 0.013566201 -0.166240908 0.808303676
item8 0.139432446 -0.016272987 0.913969888 -0.017445557
PC17 PC18 PC19 PC20
Zip 0.012354529 -0.0028835422 -0.003716220 -0.0106574467
Lat -0.017976554 -0.0056537104 0.020434011 0.0048945311
Lng -0.009532477 0.0113528349 -0.009383339 0.0093667752
Population 0.035797203 0.0019795300 0.030228291 -0.0036413349
Children 0.019900701 0.0117316494 0.020451832 0.0076524120
Age 0.001340730 -0.0123285066 0.008819602 -0.0160587167
Income 0.004632592 0.0006697662 0.013246817 -0.0048271121
Outage_sec_perweek 0.014749039 -0.0180871530 0.010967979 0.0041225283
Email 0.016182672 0.0066287580 -0.015666053 -0.0010241338
Contacts 0.003887364 -0.0262335392 0.020794425 0.0006749441
Yearly_equip_failure 0.014258890 -0.0007018728 0.007604732 0.0212155127
Tenure -0.007512632 -0.0121864765 0.006811292 -0.0050173963
MonthlyCharge 0.013137318 0.0009303910 0.020554916 0.0128927114
Bandwidth_GB_Year -0.003354044 -0.0016069488 -0.007559956 -0.0072408162
item1 0.048264506 0.0242272388 -0.239130884 -0.7930855463
item2 0.070960834 0.0683243429 -0.590745884 0.5731520773
item3 0.145692701 -0.3923196033 0.676577418 0.1769152875
item4 0.446844285 0.4313373281 0.087901118 -0.0181018442
item5 0.208115585 0.6946548884 0.261128981 0.0427600114
item6 -0.757664109 0.4049907481 0.224135917 0.0649766985
item7 0.373344791 0.0679184919 0.065585465 0.0410352738
item8 0.108536044 -0.0439036435 0.046246023 0.0431315864
PC21 PC22
Zip -0.0387970156 0.7001591779
Lat -0.0076029404 0.1122678682
Lng -0.0405912949 0.7026032290
Population -0.0009509239 0.0136809476
Children 0.0183468106 -0.0004750638
Age -0.0215670835 -0.0021850116
Income -0.0012984233 -0.0017340651
Outage_sec_perweek -0.0007812121 0.0006235514
Email -0.0056071592 0.0032365772
Contacts 0.0027855459 -0.0021232365
Yearly_equip_failure 0.0025489770 -0.0029759712
Tenure 0.7037863485 0.0411839706
MonthlyCharge 0.0483011784 -0.0002902270
Bandwidth_GB_Year -0.7056788669 -0.0392040654
item1 0.0030667994 -0.0018051388
item2 0.0032203848 -0.0038689675
item3 -0.0148755572 0.0058078082
item4 -0.0016189777 -0.0015166223
item5 0.0030792648 -0.0027467652
item6 -0.0014184860 0.0003596890
item7 0.0066637807 0.0015055095
item8 0.0028672522 0.0022335072fviz_eig(df.pca, choice = "eigenvalue", addlabels = TRUE)
---
title: "R Notebook"
output:
  html_notebook: default
  pdf_document: default
---
```{r}
#import libraries 
library(dplyr)
library(readr)
library (visdat)
library(superml)
library(plyr)
library(tidyverse)
library(factoextra)

#import data file & preview data 
df <- read_csv('/Users/Amanda.Hartzler/Desktop/Data_Analytics_Masters/D206/churn_raw_data.csv')
head(df)
```
```{r}
#determine column names, non-null values, & types 
str(df)
```
```{r}
#determine if any rows are duplicated 
duplicated(df)
```
```{r}
#delete any duplicated rows
df <- distinct(df)
print(df)
```
```{r}
#no duplicated values in dataset
#determine which variables contain null values & how many null values
 colSums(is.na(df))
```
```{r}
#visualization of missing data
vis_miss(df)
```
```{r}
#Check each column containing null values that is a float or integer value. 
#Determine skew, possible ouliers, and distribution. 
#Children Histogram
hist(df$Children, 
     main = 'Children', 
     xlab = 'Number of Children', 
     border = 'blue', 
     col = 'green', 
     xlim = c(0, 10), 
     breaks = 10)
```
```{r}
#Age Histogram
hist(df$Age)
```
```{r}
#Income Histogram
hist(df$Income)
```
```{r}
#Tenure Histogram 
hist(df$Tenure)
```
```{r}
hist(df$Tenure)
```
```{r}
#Children column is right skewed, therefore I will use the median to impute the data. 
df$Children[is.na(df$Children)]<-median(df$Children,na.rm=TRUE)

#verify the data was imputed 
colSums(is.na(df))

```
```{r}
#Check if the distribution of data was effected by the imputation of the median. 
hist(df$Children)
```
```{r}
#Age column has a uniform distribution, therefore I will use the mean to impute the data.
df$Age[is.na(df$Age)]<-mean(df$Age,na.rm=TRUE)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#Check if the distribution of data was effected by the imputation of the mean. 
hist(df$Age)
```
```{r}
#Income column has is right skewed, therefore I will use the median to impute the data.
df$Income[is.na(df$Income)]<-median(df$Income,na.rm=TRUE)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#Check if the distribution of data was effected by the imputation of the median. 
hist(df$Income)
```
```{r}
#Tenure column has a bimodal distribution, therefore I decided to use the median to impute the data. (Middleton, 2022a)  
df$Tenure[is.na(df$Tenure)]<-median(df$Tenure,na.rm=TRUE)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#Check if the distribution of data was effected by the imputation of the mean. 
hist(df$Tenure)
```
```{r}
#Bandwidth_GB_Year column has a bimodal distribution, therefore I decided to use the median to impute the data.
df$Bandwidth_GB_Year[is.na(df$Bandwidth_GB_Year)]<-median(df$Bandwidth_GB_Year,na.rm=TRUE)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#Check if the distribution of data was effected by the imputation of the mean. 
hist(df$Bandwidth_GB_Year)
```
```{r}
#Clean null values from object or text columns using the mode.
#Techie column is text, therefore I will use the mode to impute the data.
df$Techie[is.na(df$Techie)]<-mode(df$Techie)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#Phone column is text, therefore I will use the mode to impute the data.
df$Phone[is.na(df$Phone)]<-mode(df$Phone)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
#TechSupport column is text, therefore I will use the mode to impute the data.
df$TechSupport[is.na(df$TechSupport)]<-mode(df$TechSupport)

#verify the data was imputed 
colSums(is.na(df))
```
```{r}
```


```{r}
b <-boxplot(df$CaseOrder)
```
```{r}
#Using Boxplots, check for outliers in each in each float or integer value column. 
b <-boxplot(df$Zip, main = 'Zip')
b <-boxplot(df$Lat, main = 'Lat')
b <-boxplot(df$Lng, main = 'Lng')
b <-boxplot(df$Population, main = 'Population')
b <-boxplot(df$Children, main = 'Children')
b <-boxplot(df$Age, main = 'Age')
b <-boxplot(df$Income, main = 'Income')
b <-boxplot(df$Outage_sec_perweek, main = 'Outage_sec_perweek')
b <-boxplot(df$Email, main = 'Email')
b <-boxplot(df$Contacts, main = 'Contacts')
b <-boxplot(df$Yearly_equip_failure, main = 'Yearly_equip_failure')
b <-boxplot(df$Tenure, main = 'Tenure')
b <-boxplot(df$MonthlyCharge, main = 'MonthlyCharge')
b <-boxplot(df$Bandwidth_GB_Year, main = 'Bandwidth_GB_Year')
b <-boxplot(df$item1, main = 'item1')
b <-boxplot(df$item2, main = 'item2')
b <-boxplot(df$item3, main = 'item3')
b <-boxplot(df$item4, main = 'item4')
b <-boxplot(df$item5, main = 'item5')
b <-boxplot(df$item6, main = 'item6')
b <-boxplot(df$item7, main = 'item7')
b <-boxplot(df$item8, main = 'item8')
```
```{r}
#Outliers found in Lat, Lng, Population, Children, Income, Outage_sec_perweek, Email, Contacts, Yearly_equip_failure, MonthlyCharge, item1, item2, item3, item4, item5, item6, item7, & item8 columns. 
#Treating outliers: 
max(df$Lat)
min(df$Lat)
```
```{r}
#Retain outliers in Lat (Incuding US territories, the min and max are within a valid range) (Bathman, 2018)
max(df$Lng)
min(df$Lng)
```
```{r}
#Retain outliers in Lng (Incuding US territories, the min and max are within a valid range) (Bathman, 2018)
summary(df$Population)
```
```{r}
#Replace outlier population values > 27,000 
#New York City, NY, has the most density population in the US. In New York the max population density is a little over 27,000 per square mile. Therefore the right skewed outliers are likely entry errors. (Planning-Population-NYC Population Facts - DCP, n.d.)
df["Population"][df["Population"] >= 27000] <- 2931
summary(df$Population)
```
```{r}
#Check distribution of population data. 
b <-boxplot(df$Population, main = 'Population')
```
```{r}
#Check that the max income is within a reasonable range
max(df$Income)

#Check that the max and min outage_sec_perweek is within a reasonable range
max(df$Outage_sec_perweek)
min(df$Outage_sec_perweek)
```
```{r}
#Retain outliers in Children (All values are possible children values)
#Retain outliers in Income (All values are possible income values)
summary(df$Outage_sec_perweek)
```
```{r}
#Replace negative outliers in Outage_sec_perweek with median because you cannot have less than zero secons of outage
df$Outage_sec_perweek[df$Outage_sec_perweek <0] <- 10.214231
summary(df$Population)
```
```{r}
b <-boxplot(df$Outage_sec_perweek, main = 'Outage_sec_perweek')
```
```{r}
#Check that the MonthlyCharge income is within a reasonable range
max(df$MonthlyCharge)
```
```{r}
#Retain outliers in Email (All values are possible email values)
#Retain outliers in Contacts (All values are possible contact values)
#Retain outliers in Yearly_equip_failure (All values are possible equipment failure values)
#Retain outliers in MonthlyCharge (All values are possible monthly charge values)
#Retain outliers in all item answers (All values are possible values for each item answer)
```
```{r}
#Re-expressing Categorical Variables (Middleton, 2022c)
#Practice label encoding yes/no dichotomous binary columns. (By Great Learning Team -, 2022)
lbl = LabelEncoder$new()
df$Churn = lbl$fit_transform(df$Churn)
print(df$Churn)
```
```{r}
df$Techie = lbl$fit_transform(df$Techie)
df$Port_modem = lbl$fit_transform(df$Port_modem)
df$Phone = lbl$fit_transform(df$Phone)
```
```{r}
#Practice Ordinal Encoding (Middleton, 2022c)
#First find unique entiries in the education table. 
print(unique(df$Education))
print(length(unique(df$Education)))
```
```{r}
edu.num <- revalue(x = df$Education, replace = c('No Schooling Completed'= 0, 'Nursery School to 8th Grade'= 1, '9th Grade to 12th Grade, No Diploma'= 2, 'GED or Alternative Credential'= 3, 'Regular High School Diploma'= 4, 'Some College, Less than 1 Year'= 5, 'Some College, 1 or More Years, No Degree'= 6, "Associate's Degree"= 7, 'Professional School Degree'= 8, "Bachelor's Degree"= 9, "Master's Degree"= 10, 'Doctorate Degree'= 11))
df$Education_numeric <- as.numeric(edu.num)
```
```{r}
#Check that Education_numeric was created correctly.
unique(df$Education_numeric)
```
```{r}
#Principal Component Analysis
data.frame(colnames(df))
```
```{r}
#Principal Component Analysis
features <- df[,c(8, 9, 10, 11, 15, 16, 19, 23, 24, 25, 26, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52)]
print(features)
```
```{r}
df.pca<- prcomp(df[,c(8, 9, 10, 11, 15, 16, 19, 23, 24, 25, 26, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52)], center = TRUE, scale = TRUE)
```
```{r}
df.pca$rotation
```
```{r}
fviz_eig(df.pca, choice = "eigenvalue", addlabels = TRUE)
```

